Multi-Frequency Radar Fusion for Weather-Robust Point Clouds

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in object detection and ranging due to the limitations of either high frequency or low frequency radar signals, particularly in varying weather conditions and environments, which affect the quality and resolution of data collected.

Innovation Solution

The use of both high frequency and low frequency radar signals, processed using specific parameters and correlation functions, to generate a comprehensive 'point-cloud' dataset that adapts to the strengths and weaknesses of each frequency, enhancing object detection and velocity identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high frequency radar signals are used, then resolution and detection precision are improved, but reliability in varying weather conditions deteriorates

Engineering Contradiction:
Improvedetection precisionVSAvoidreliability in weather conditions
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent combines high frequency radar signals (77 GHz) and low frequency radar signals (24 GHz) into a unified point cloud dataset. By merging the high resolution data from 77 GHz radar with the weather-resilient data from 24 GHz radar, the system achieves both high detection precision and reliability across varying weather conditions.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent processes high frequency and low frequency radar signals using different parameters and correlation functions optimized for each frequency band. This allows the system to extract maximum information from each frequency while adapting to their respective strengths and weaknesses in different environmental conditions.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If low frequency radar signals are used, then reliability in varying weather conditions is improved, but detection precision and resolution deteriorate

Engineering Contradiction:
Improvereliability in weather conditionsVSAvoiddetection precision
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent merges low frequency radar data (24 GHz) which provides reliable detection in varying weather conditions with high frequency radar data (77 GHz) which provides high resolution. The combination allows the system to maintain reliability across weather conditions while achieving high detection precision through the complementary strengths of both frequencies.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent applies frequency-specific processing parameters and correlation functions to low frequency signals, then integrates these processed results with high frequency data. This parameter optimization ensures that low frequency signals contribute their weather resilience while the overall system achieves high precision through multi-frequency fusion.

Inventive Principle:
Principle #35Parameter changes

3Device complexity

If only single frequency radar signals are used, then device complexity is reduced, but adaptability to different environments deteriorates

Engineering Contradiction:
Improvedevice complexityVSAvoidadaptability to environments
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent merges data from multiple radar frequencies into a single unified point cloud dataset, allowing the system to adapt to different environmental conditions by leveraging the complementary characteristics of each frequency band while maintaining a relatively simple device architecture.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent creates a universal processing framework that handles both high frequency and low frequency radar signals through a common pipeline of preprocessing, downsampling, upsampling, and correlation functions. This multi-functional approach allows the same system to adapt to various environmental conditions without requiring separate processing systems for each frequency.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach generates higher quality data sets by leveraging the strengths of both frequencies, improving object detection and ranging capabilities in diverse conditions, and reducing false detections by cross-referencing data from both high and low frequency radar signals.

Implementation Method 1

A radar apparatus may be configured to transmit a first set of radar signals

Methodology Applied
Scientific EffectRadar: Radar

Implementation Method 2

receive a set of reflected radar signals

Methodology Applied
Scientific EffectReflection: Reflection

Data Source

PatentUS12122415B2Multiple frequency fusion for enhanced point cloud formation
Publication Date: 2024.10.22 GM CRUISE HOLDINGS LLC
  • US12122415B2 patent drawing
  • US12122415B2 patent drawing
  • US12122415B2 patent drawing

AI summary

Methods and apparatus disclosed within provide a solution to problems associated with the use of either high frequency or low frequency radar signals. Methods of the present disclosure may transmit high frequency radar signals, transmit low frequency radar signals, receive reflected radar signals, and process the received radar signals using parameters respectively suited for processing high frequency and low frequency radar signals. Evaluations may be performed that allow an apparatus to adapt for limitations associated with the processing of high frequency radar data, the processing of low frequency radar data, or both. Different correlation functions may be performed that allow the apparatus to identify objects and to identify object velocities using different sets of program code instructions. These different evaluations and correlations may result in the generation of a set of “point-cloud” information that may be used by other processes of a sensing apparatus.